Computational Statistics Project
Department of Economics, Vienna University of Economics and Business (WU Vienna)
May 27, 2025
A Markov chain is a stochastic process \(\{X_t\}\) indexed by time \(t\geq 0\).
Markov Chain Monte Carlo (MCMC) methods make use of Markov chains to sample from a target distribution.
Markov chains are
For such Markov Chains, transition probabilities converge to a unique stationary distribution on the state space.
Metropolis-Hastings is a class of MCMC methods.
The Gibbs sampler is an example of a Metropolis-Hastings algorithm.
Hamiltonian Monte Carlo
The No-U-Turn-Sampler (NUTS)
This list is scrollable.